From 8bcd404818ef2a30c2be99ab41228db423eaced1 Mon Sep 17 00:00:00 2001 From: teridon Date: Mon, 10 Jan 2022 16:36:05 -0500 Subject: [PATCH] [digitalconcerthall] Add extractor (#1931) Authored by: teridon --- yt_dlp/extractor/common.py | 1 + yt_dlp/extractor/digitalconcerthall.py | 143 +++++++++++++++++++++++++ yt_dlp/extractor/extractors.py | 1 + 3 files changed, 145 insertions(+) create mode 100644 yt_dlp/extractor/digitalconcerthall.py diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 7c83991ea3..3a61eecc13 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -375,6 +375,7 @@ class InfoExtractor(object): disc_number: Number of the disc or other physical medium the track belongs to, as an integer. release_year: Year (YYYY) when the album was released. + composer: Composer of the piece Unless mentioned otherwise, the fields should be Unicode strings. diff --git a/yt_dlp/extractor/digitalconcerthall.py b/yt_dlp/extractor/digitalconcerthall.py new file mode 100644 index 0000000000..9b302a9a07 --- /dev/null +++ b/yt_dlp/extractor/digitalconcerthall.py @@ -0,0 +1,143 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +from ..utils import ( + ExtractorError, + parse_resolution, + traverse_obj, + try_get, + urlencode_postdata, +) + + +class DigitalConcertHallIE(InfoExtractor): + IE_DESC = 'DigitalConcertHall extractor' + _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P[a-z]+)/concert/(?P[0-9]+)' + _OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token' + _ACCESS_TOKEN = None + _NETRC_MACHINE = 'digitalconcerthall' + _TESTS = [{ + 'note': 'Playlist with only one video', + 'url': 'https://www.digitalconcerthall.com/en/concert/53201', + 'info_dict': { + 'id': '53201-1', + 'ext': 'mp4', + 'composer': 'Kurt Weill', + 'title': '[Magic Night]', + 'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$', + 'upload_date': '20210624', + 'timestamp': 1624548600, + 'duration': 2798, + 'album_artist': 'Members of the Berliner Philharmoniker / Simon Rössler', + }, + 'params': {'skip_download': 'm3u8'}, + }, { + 'note': 'Concert with several works and an interview', + 'url': 'https://www.digitalconcerthall.com/en/concert/53785', + 'info_dict': { + 'id': '53785', + 'album_artist': 'Berliner Philharmoniker / Kirill Petrenko', + 'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich', + }, + 'params': {'skip_download': 'm3u8'}, + 'playlist_count': 3, + }] + + def _login(self): + username, password = self._get_login_info() + if not username: + self.raise_login_required() + token_response = self._download_json( + self._OAUTH_URL, + None, 'Obtaining token', errnote='Unable to obtain token', data=urlencode_postdata({ + 'affiliate': 'none', + 'grant_type': 'device', + 'device_vendor': 'unknown', + 'app_id': 'dch.webapp', + 'app_version': '1.0.0', + 'client_secret': '2ySLN+2Fwb', + }), headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + }) + self._ACCESS_TOKEN = token_response['access_token'] + try: + self._download_json( + self._OAUTH_URL, + None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({ + 'grant_type': 'password', + 'username': username, + 'password': password, + }), headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + 'Referer': 'https://www.digitalconcerthall.com', + 'Authorization': f'Bearer {self._ACCESS_TOKEN}' + }) + except ExtractorError: + self.raise_login_required(msg='Login info incorrect') + + def _real_initialize(self): + self._login() + + def _entries(self, items, language, **kwargs): + for item in items: + video_id = item['id'] + stream_info = self._download_json( + self._proto_relative_url(item['_links']['streams']['href']), video_id, headers={ + 'Accept': 'application/json', + 'Authorization': f'Bearer {self._ACCESS_TOKEN}', + 'Accept-Language': language + }) + + m3u8_url = traverse_obj( + stream_info, ('channel', lambda x: x.startswith('vod_mixed'), 'stream', 0, 'url'), get_all=False) + formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False) + self._sort_formats(formats) + + yield { + 'id': video_id, + 'title': item.get('title'), + 'composer': item.get('name_composer'), + 'url': m3u8_url, + 'formats': formats, + 'duration': item.get('duration_total'), + 'timestamp': traverse_obj(item, ('date', 'published')), + 'description': item.get('short_description') or stream_info.get('short_description'), + **kwargs, + 'chapters': [{ + 'start_time': chapter.get('time'), + 'end_time': try_get(chapter, lambda x: x['time'] + x['duration']), + 'title': chapter.get('text'), + } for chapter in item['cuepoints']] if item.get('cuepoints') else None, + } + + def _real_extract(self, url): + language, video_id = self._match_valid_url(url).group('language', 'id') + if not language: + language = 'en' + + thumbnail_url = self._html_search_regex( + r'(https?://images\.digitalconcerthall\.com/cms/thumbnails/.*\.jpg)', + self._download_webpage(url, video_id), 'thumbnail') + thumbnails = [{ + 'url': thumbnail_url, + **parse_resolution(thumbnail_url) + }] + + vid_info = self._download_json( + f'https://api.digitalconcerthall.com/v2/concert/{video_id}', video_id, headers={ + 'Accept': 'application/json', + 'Accept-Language': language + }) + album_artist = ' / '.join(traverse_obj(vid_info, ('_links', 'artist', ..., 'name')) or '') + + return { + '_type': 'playlist', + 'id': video_id, + 'title': vid_info.get('title'), + 'entries': self._entries(traverse_obj(vid_info, ('_embedded', ..., ...)), language, + thumbnails=thumbnails, album_artist=album_artist), + 'thumbnails': thumbnails, + 'album_artist': album_artist, + } diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py index ccd9e7a7f5..889e8229ce 100644 --- a/yt_dlp/extractor/extractors.py +++ b/yt_dlp/extractor/extractors.py @@ -380,6 +380,7 @@ from .duboku import ( ) from .dumpert import DumpertIE from .defense import DefenseGouvFrIE +from .digitalconcerthall import DigitalConcertHallIE from .discovery import DiscoveryIE from .discoverygo import ( DiscoveryGoIE,